Update app.py

app.py

@@ -28,6 +28,7 @@ from langchain_huggingface.llms import HuggingFacePipeline
 import re
 from langchain_huggingface.llms import HuggingFacePipeline
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline,BitsAndBytesConfig,TextIteratorStreamer
+from langchain_cerebras import ChatCerebras
 
 
 # Configure logging
@@ -135,18 +136,23 @@ retriever = db.as_retriever(
 # )
 
 
-llm = ChatOpenAI(
-    # base_url="https://openrouter.ai/api/v1",
-    base_url="https://api.cerebras.ai/v1/chat/completions",
-    temperature=0,
-    api_key=C_apikey,
-    model="llama-3.3-70b",
-    max_tokens=None,
-    timeout=None,
-    stream=True
+# llm = ChatOpenAI(
+#     base_url="https://openrouter.ai/api/v1",
+#     temperature=0,
+#     api_key=ChatOpenAI,
+#     model="google/gemini-2.0-flash-thinking-exp:free",
+#     max_tokens=None,
+#     timeout=None,
+#     stream=True
     
-)
+# )
+
 
+llm = ChatCerebras(
+    model="llama-3.3-70b",
+    api_key=C_apikey,
+    stream=true
+)